3D FACE MODEL CONSTRUCTION BASED ON KINECT FOR FACE RECOGNITION

[[abstract]]We propose a simpler and faster method to recognize face. First, we use Kinect to detect frontal face and get depth image information with face, then we portrayed face in OpenGL to construct a three-dimensional face model based on the depth information. The face model also retains texture information of the original face images, and to create a complete change depth of face. It has a good result of repairing the distortion in side face. We can get a set face images with different angles by the method proposed, In recognition part, we use PCA(Principal Component Analysis) to reduce the dimensions, and classified with SVM(Support Vector Machine). The experiments show that the side face recognition can have good results.[[sponsorship]]National Taipei University[[conferencetype]]國際[[conferencedate]]20150718~20150719[[booktype]]電子版[[iscallforpapers]]Y[[conferencelocation]]Tokyo, Japa